Why did we open-source our inference engine? Read the post

intfloat/e5-mistral-7b-instruct

Improving Text Embeddings with Large Language Models. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei, arXiv 2024

Overview

Architecture
Mistral
Parameters
7.1B
Tasks
Encode
Outputs
Dense
Dimensions
Dense: 4,096
Max Sequence Length
4,096 tokens
License
mit
Languages
en

Benchmarks

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.3932
map at 10 0.1477
mrr at 10 0.6024
Performance L4 b1 c16
Corpus 3.1K tok/s
Corpus p50 1.2s
Query 212 tok/s
Query p50 230.4ms
Reference →

NanoFiQA2018Retrieval

finance retrieval en

Smaller subset of the FiQA financial QA dataset

Quality
ndcg at 10 0.5960
map at 10 0.5317
mrr at 10 0.6404
Performance L4 b1 c16
Corpus 2.9K tok/s
Corpus p50 670.1ms
Query 466 tok/s
Query p50 224.6ms
Reference →

Self-hosted inference for search & document processing

Cut API costs by 50x, boost quality with 85+ SOTA models, and keep your data in your own cloud.

Github 2.0K

Contact us

Tell us about your use case and we'll get back to you shortly.